Image processing method, image processing apparatus

Abstract

A processor selects a target sheet from a plurality of predetermined sheet candidates in accordance with selection information that is input via an input device. Furthermore, the processor derives feature information regarding a noise point from a target image that is obtained through an image reading process performed on an output sheet output from an image forming device, the noise point being a dot-like noise image included in the target image. Furthermore, the processor determines whether or not the noise point is a dot-like sheet noise by applying the feature information to a determination algorithm that corresponds to the target sheet, the sheet noise being included in a sheet of the output sheet itself, the determination algorithm being one of a plurality of determination algorithms that respectively correspond to the plurality of sheet candidates.

The invention claimed is: 
     
       1. An image processing method comprising:
 a processor selecting a target sheet from a plurality of predetermined sheet candidates in accordance with selection information that is input via an input device; 
 the processor deriving feature information regarding a noise point from a target image that is obtained through an image reading process performed on an output sheet output from an image forming device, the noise point being a dot-like noise image included in the target image; and 
 the processor executing a sheet noise determination process to determine whether or not the noise point is a dot-like sheet noise by applying the feature information to a determination algorithm that corresponds to the target sheet, the sheet noise being included in a sheet of the output sheet itself, the determination algorithm being one of a plurality of determination algorithms that respectively correspond to the plurality of sheet candidates, wherein 
 the processor deriving the feature information includes identifying, as the feature information, a degree of coincidence or difference of a piece of detection color information that corresponds to a color of the noise point in the target image, with respect to one or more pieces of predetermined reference color information corresponding to one or more developing colors used in the image forming device 
 the one or more pieces of reference color information are one or more reference color vectors that correspond to the one or more developing colors in a color space, 
 the piece of detection color information is a detection color vector that represents a vector in the color space from one of a color of the noise point in the target image and a color of a reference area including a periphery of the noise point to the other, and 
 the processor identifies, as the feature information, a degree of coincidence or difference of the detection color vector with respect to the reference color vectors. 
 
     
     
       2. An image processing method comprising:
 a processor selecting a target sheet from a plurality of predetermined sheet candidates in accordance with selection information that is input via an input device; 
 the processor deriving feature information regarding a noise point from a target image that is obtained through an image reading process performed on an output sheet output from an image forming device, the noise point being a dot-like noise image included in the target image; and 
 the processor executing a sheet noise determination process to determine whether or not the noise point is a dot-like sheet noise by applying the feature information to a determination algorithm that corresponds to the target sheet, the sheet noise being included in a sheet of the output sheet itself, the determination algorithm being one of a plurality of determination algorithms that respectively correspond to the plurality of sheet candidates, wherein 
 the processor deriving the feature information includes:
 generating an extraction image by extracting the noise point from the target image; and 
 deriving, as the feature information, a degree of flatness of the noise point in the extraction image. 
 
 
     
     
       3. The image processing method according to  claim 1 , wherein
 the processor deriving the feature information includes: 
 generating an extraction image by extracting the noise point from the target image; and 
 deriving, as the feature information, an edge strength of the noise point in the extraction image. 
 
     
     
       4. The image processing method according to  claim 1 , wherein
 the processor deriving the feature information includes: 
 generating an extraction image by extracting the noise point from the target image; and 
 deriving, as the feature information, a number of edges that is a number of positions in a transverse pixel sequence where variation of a pixel value exceeds an acceptable range, the transverse pixel sequence being a pixel sequence traversing the noise point in the extraction image. 
 
     
     
       5. The image processing method according to  claim 1 , wherein
 the processor executing the sheet noise determination process includes 
 determining whether or not the noise point is the sheet noise by comparing a value of the feature information or an evaluation value of the feature information with a predetermined threshold. 
 
     
     
       6. The image processing method according to  claim 1 , wherein
 the processor executing the sheet noise determination process includes 
 determining whether or not the noise point is the sheet noise by applying a value of the feature information or an evaluation value of the feature information as an input parameter of a learning model that has been preliminarily learned using, as teacher data, a plurality of pieces of sample data corresponding to sheet noises. 
 
     
     
       7. The image processing method according to  claim 1 , wherein
 the processor deriving the feature information includes: 
 generating an extraction image by extracting the noise point from the target image; and 
 deriving, as the feature information, an image of a target area including the noise point in the extraction image, and 
 the processor executing the sheet noise determination process includes 
 executing a sheet noise pattern recognition process in which the image of the target area is treated as an input image, and it is determined whether or not the input image is an image corresponding to the sheet noise by performing a pattern recognition on the input image. 
 
     
     
       8. An image processing method comprising:
 a processor selecting a target sheet from a plurality of predetermined sheet candidates in accordance with selection information that is input via an input device; 
 the processor deriving feature information regarding a noise point from a target image that is obtained through an image reading process performed on an output sheet output from an image forming device, the noise point being a dot-like noise image included in the target image; and 
 the processor executing a sheet noise determination process to determine whether or not the noise point is a dot-like sheet noise by applying the feature information to a determination algorithm that corresponds to the target sheet, the sheet noise being included in a sheet of the output sheet itself, the determination algorithm being one of a plurality of determination algorithms that respectively correspond to the plurality of sheet candidates, wherein 
 the processor deriving the feature information includes:
 generating an extraction image by extracting the noise point from the target image; and 
 deriving, as the feature information, an image of a target area including the noise point in the extraction image, 
 
 the processor executing the sheet noise determination process includes executing a sheet noise pattern recognition process in which the image of the target area is treated as an input image, and it is determined whether or not the input image is an image corresponding to the sheet noise by performing a pattern recognition on the input image, and 
 in the sheet noise pattern recognition process, it is determined whether or not the input image is the image corresponding to the sheet noise based on a learning model that has been preliminarily learned using, as teacher data, a plurality of sample images corresponding to sheet noises. 
 
     
     
       9. The image processing method according to  claim 2 , wherein
 the processor generating the extraction image includes: 
 generating a first pre-process image by executing a first pre-process using a horizontal direction of the test image as a predetermined processing direction, the first pre-process including a main filter process in which a pixel value of each of focused pixels sequentially selected from the test image is converted to a conversion value that is obtained by performing a process to emphasize a difference between a pixel value of a focused area including the focused pixels and a pixel value of two adjacent areas that are adjacent to the focused area from opposite sides in the processing direction; 
 generating a second pre-process image by executing a second pre-process that includes the main filter process in which a vertical direction of the test image is used as the processing direction; and 
 generating, as the extraction image, an image by extracting, as the noise point, a specific part that is common to the first pre-process image and the second pre-process image, from specific parts which are each composed of one or more significant pixels and are present in the first pre-process image and the second pre-process image. 
 
     
     
       10. The image processing method according to  claim 9 , wherein
 the first pre-process includes: 
 generating first main map data by executing the main filter process using the horizontal direction as the processing direction; 
 generating horizontal edge strength map data by executing an edge emphasizing filter process on the focused area and one of the two adjacent areas on the test image, using the horizontal direction as the processing direction; and 
 generating the first pre-process image by correcting each pixel value of the first main map data by each corresponding pixel value of the horizontal edge strength map data, and 
 the second pre-process includes: 
 generating second main map data by executing the main filter process using the vertical direction as the processing direction; 
 generating vertical edge strength map data by executing the edge emphasizing filter process on the focused area and one of the two adjacent areas on the test image, using the vertical direction as the processing direction; and 
 generating the second pre-process image by correcting each pixel value of the second main map data by each corresponding pixel value of the vertical edge strength map data. 
 
     
     
       11. An image processing apparatus comprising the processor that executes processes of the image processing method according to  claim 1 .